Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MCKRUZ/ComfyUI-Expert --skill comfyui-character-gengit clone --depth 1 https://github.com/MCKRUZ/ComfyUI-ExpertWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-character-gen)<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-character-gen"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-character-gen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-character-gen"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-character-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00141 | $0.02534 |
| Opus 5 | $0.00071 | $0.01267 |
| Sonnet 5 | $0.00028 | $0.00507 |
| Haiku 4.5 | $0.00014 | $0.00253 |
Grade A, and why
comfyui-character-gen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Character Generation Expert
Build production-ready ComfyUI workflows for consistent character generation across image, video, and voice modalities.
Quick Decision: Which Approach?
Starting from reference images (like 3D renders)? → InfiniteYou (state-of-the-art 2025) or InstantID + IP-Adapter (proven, lower VRAM)
Need highest identity fidelity? → FLUX.2 (NEW 2026: up to 10 ref images) or PuLID Flux II (no model pollution)
Want iterative editing without retraining? → FLUX Kontext (context-aware, maintains consistency across edits)
Creating video content? → LTX-2 (NEW 2026: 4K production-ready), Wan 2.2 MoE (film-level), or FramePack (60-sec on 6GB!)
Need voice for character? → TTS Audio Suite (unified platform, 23 languages) or F5-TTS Cross-Lingual (NEW 2026)
Core Workflow Patterns
Pattern 1: Zero-Shot Character Generation (No Training)
Best for: Quick iteration, 3D-to-photorealism conversion, limited reference images
Load Reference Face → InstantID + IP-Adapter FaceID → ControlNet Pose → KSampler → FaceDetailer → Upscale
Critical settings:
- CFG: 4-5 (prevents burning with InstantID)
- Resolution: 1016×1016 (avoids watermark artifacts)
- IP-Adapter weight: 0.6-0.8
- InstantID noise injection: 35% to negative
See references/workflows.md for complete node configurations.
Pattern 2: LoRA + Identity Methods (Maximum Consistency)
Best for: Production work, character series, video generation base
Train LoRA → Load LoRA + Checkpoint → Add InstantID/PuLID → Generate → FaceDetailer → ReActor (optional) → Upscale
Training requirements:
- 15-30 images, varied poses/expressions/lighting
- Unique trigger word (e.g., "sage_character")
- See
references/lora-training.mdfor full parameters
Pattern 3: Video Generation Pipeline
Best for: Talking heads, character animation, promotional content
Generate/Load Hero Image → Wan 2.1 I2V OR AnimateDiff → FaceDetailer per frame → Frame Interpolation → Video Combine
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- eval/benchmark.yaml 1.3 KB
- eval/EVAL.md 2.2 KB
- eval/results/.gitignore 83 B
- eval/results/.gitkeep 0 B
- eval/run-eval.sh 18 KB runs code
- eval/test-cases.yaml 7.3 KB
- eval/trigger-tests.yaml 1.9 KB
- references/evolution.md 6.7 KB
- references/lora-training.md 8.9 KB
- references/models.md 8.4 KB
- references/research-2025.md 18 KB
- references/talking-head-workflows.md 27 KB
- references/voice-synthesis.md 10 KB
- references/workflows.md 9.7 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 220 lines · 141 tokens per session scan A b16902d4ef6b
comfyui-character-gen is a skill published in the GitHub repository MCKRUZ/ComfyUI-Expert (91 stars, last pushed 5mo ago), licensed MIT. It adds 141 tokens to every session and 2,534 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…
handoff
Work with Master Canvas AI video handoff packages. Use when a user provides a Master Canvas ZIP or projectmanifest.json and wants Hermes to inspect assets, preserve scene and shot order, prepare ComfyUI/LTX 2.3 jobs, or hand off prompts to Kling, Veo, or another video generation operator. Also use when a user wants…
local-ai-film
A directing workflow for producing AI short films with local or cloud-based models, including atmospheric films, trailers, vlogs, and dialogue-driven stories. It covers creative decisions, avoiding repetitive results, production steps, and final editing.
rhythm-density
A video-editing guide for arranging several short locally generated shots so their pacing alternates between quick, dense sections and slower breathing space.